To reduce the cost of virtual try-on, a method of image deformation by body part size is proposed for the traditional two-dimensional virtual try-on method, which is challenging to represent the personalized characteristics of the body size of the fitting subject. On the basis of the input information of the user's body size, the method can generate a fitting effect that shows the user's characteristics with the corresponding clothes. The image segmentation algorithm is used to snap out the garment from the background garment image, and then the size and position of the garment are adjusted according to the dressing position of the standard mannequin image and fit the mannequin image. The final mesh with dense vertices is generated using surface subdivision. The experimental results show that this method can show good results in user personalized try-on.

中文翻译：

---

个性化着装二维虚拟试穿算法及应用研究

为降低虚拟试穿成本，针对传统的二维虚拟试穿方法难以体现试衣主体体型个性化特征的问题，提出了一种通过身体部位尺寸进行图像变形的方法。基于用户的体型信息的输入，该方法可以生成显示用户特征与相应衣服的试衣效果。利用图像分割算法从背景服装图像中截取服装，然后根据标准人体模型图像的着装位置调整服装的尺寸和位置，使服装与人体模型图像相吻合。使用表面细分生成具有密集顶点的最终网格。